Abstract
Similar to linear models, neural network are differentiable parameterized functions, and are trained using gradient-based optimization (see Section 2.8). The objective function for nonlinear neural networks is not convex, and gradient-based methods may get stuck in a local minima. Still, gradient-based methods produce good results in practice.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Goldberg, Y. (2017). Neural Network Training. In: Neural Network Methods for Natural Language Processing. Synthesis Lectures on Human Language Technologies. Springer, Cham. https://doi.org/10.1007/978-3-031-02165-7_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-02165-7_5
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-01037-8
Online ISBN: 978-3-031-02165-7
eBook Packages: Synthesis Collection of Technology (R0)eBColl Synthesis Collection 7